Collibra Atlas
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ATLAS_EMBED_BACKEND | No | Override embedding backend. Values: auto, apple, nvidia, cpu. | auto |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_docsA | Semantic search across documentation. Best for conceptual or 'how do I' queries. Returns top-k chunks with file paths, headings, and similarity scores. |
| search_codeA | Semantic search restricted to code examples in the docs. Useful for 'show me a script that does X'. |
| get_chunkA | Fetch a single chunk by its ID. Use after a search_docs call to get the full content of a specific hit. |
| get_bundle_infoA | Return the bundle manifest: source repo/branch/SHA, build date, chunk count, embedding model. Use to cite freshness. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a distinct purpose: search_docs and search_code target different content types, get_chunk retrieves specific chunks by ID, and get_bundle_info provides metadata. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern: search_docs, search_code, get_chunk, get_bundle_info. This makes the API predictable and easy to learn.
Four tools is well-scoped for a documentation search and retrieval server. Each tool serves a clear function without unnecessary bloat or missing essentials.
The toolset covers the full workflow: searching across documentation, searching code examples, retrieving full chunks, and checking metadata for freshness. No critical gaps for the intended use case.